Fix executorch kv cache incompatibility with to_executorch lowering

[dvorjackz]

Summary

Fix the Llama 3.2 vision text decoder prefill issue by marking the kv cache as an initialized mutable buffer in a custom pass

Test plan

• Add kv_cache export tests that test accuracy against torchtune eager and verify contents of the cache after prefill and token-by-token generation
• Export and run full Llama 3.2 vision text decoder

> python -m examples.models.llama.export_llama --model llama3_2_vision --checkpoint /tmp/Llama-3.2-11B-Vision-Instruct/original/consolidated.pth --params examples/models/llama3_2_vision/text_decoder/params/demo_config.json  --metadata '{"append_eos_to_prompt": 0, "get_bos_id":128000, "get_eos_ids":[128009, 128001], "get_n_bos": 0, "get_n_eos": 0}' --output_name="llama3_2_vision.pte" -d fp32 --verbose --max_seq_length 64 -k
> python -m examples.models.llama3_2_vision.runner.native --model llama3_2_vision --pte llama3_2_vision.pte  --tokenizer /tmp/Llama-3.2-11B-Vision-Instruct/original/tokenizer.model --prompt "Who's the founder of Meta?" --params examples/models/llama3_2_vision/text_decoder/params/demo_config.json --max_len 64 -kv --temperature 0

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7279

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 1 New Failure

As of commit a2b7ee3 with merge base 3ef78ee ():

NEW FAILURE - The following job has failed:

• pull / unittest-arm / linux-job (gh)
  RuntimeError: Command docker exec -t 05158f13e27680f9f23f9f4ddff63d7c19718c32d1bfedafd245a98141630ab7 /exec failed with exit code 127

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[dbort]

Please add unit tests for this logic; tests that would have broken before this fix, and would have caught this kv cache incompatibility

[dbort]

Please add unit tests for this new file

[facebook-github-bot]

@dvorjackz has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.